Skip to main content
Glama

Embeddings, Rerank & Speech-to-Text (Tanod)

text_to_speech

Idempotent

mlpeek: Speak text aloud in 41 voices: English, Spanish, French, Hindi, Italian, Portuguese. For audio to text use transcribe_audio. Returns the text spoken as audio. Offline neural TTS (Kokoro-82M); the audio is a synthetic voice. At most 2,000 characters; 41 voices in 6 languages (the voice sets the language: write the text in it). Bad input is a 422, a busy or unavailable model a 503, a synthesis over the time limit a 504 (none charged). Save data_base64 to a file to play it, or send output "url" for a 24 h link. Typically 4-10 s for 200 characters (about 13 s of speech), up to about a minute for 2,000 characters. Price: USD 0.005. Free: 5 mlpeek calls per IP per UTC day. The submitted text is not logged; the result is kept only with output "url" (24 h). Docs: https://tanod.dev/learn/text-to-speech-api.html

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "text": "<text>"
    },
    "name": "text_to_speech"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYesText to speak, 1 to 2,000 characters, in the language of the chosen voice (English, Spanish, French, Hindi, Italian or Brazilian Portuguese).
speedNoSpeaking rate, 0.5 to 2.0 (1.0 is normal).
voiceNoVoice (41): the first letter is the language: a US English (af_heart default, af_bella, am_adam), b UK English (bf_emma, bm_george), e Spanish (ef_dora), f French (ff_siwis), h Hindi (hf_alpha, hm_omega), i Italian (if_sara, im_nicola), p Brazilian Portuguese (pf_dora, pm_alex); f = female, m = male. Write the text in the voice's language.af_heart
formatNoAudio format: mp3, wav (16-bit PCM) or ogg (Opus).mp3
outputNobase64 (default): inline. url: stored for 24 hours; link, metadata.base64

Output Schema

NameRequiredDescriptionDefault
urlNo
bytesNo
charsNo
errorNoOnly on an error result: an object {code, message}, or the reason string of an x402 PaymentRequired object.
speedNo
voiceNo
engineNo
formatNo
sha256No
duration_sNo
expires_atNo
data_base64No
sample_rateNo
content_typeNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed11 schema fields changed
    • removedInput schema / properties / format / title
      Removed value: -"Format"
    • removedInput schema / properties / output / title
      Removed value: -"Output"
    • removedInput schema / properties / speed / title
      Removed value: -"Speed"
    • removedInput schema / properties / text / title
      Removed value: -"Text"
    • removedInput schema / properties / voice / title
      Removed value: -"Voice"
    • removedInput schema / title
      Removed value: -"text_to_speechArguments"
    • removedOutput schema / properties / bytes / description
      Removed value: -"Bytes."
    • removedOutput schema / properties / content_type / description
      Removed value: -"MIME type."
    • removedOutput schema / properties / expires_at / description
      Removed value: -"UTC expiry."
    • removedOutput schema / properties / sha256 / description
      Removed value: -"SHA-256."
    • removedOutput schema / properties / url / description
      Removed value: -"Public link."
  2. Changed6 schema fields changed
    • changedInput schema / properties / output / description
      Previous value: -"base64 (default): the file comes back inline as base64. url: the file is stored for 24 hours and the reply carries a download link (url, expires_at, bytes, content_type, sha256) instead of the base64, which keeps the file out of your context window."New value: +"base64 (default): inline. url: stored for 24 hours; link, metadata."
    • addedOutput schema / properties / bytes / description
      Added value: +"Bytes."
    • addedOutput schema / properties / content_type / description
      Added value: +"MIME type."
    • addedOutput schema / properties / expires_at / description
      Added value: +"UTC expiry."
    • addedOutput schema / properties / sha256 / description
      Added value: +"SHA-256."
    • addedOutput schema / properties / url / description
      Added value: +"Public link."
  3. Changed4 schema fields changed
    • addedInput schema / properties / output
      Added value: +{
      +  "default": "base64",
      +  "description": "base64 (default): the file comes back inline as base64. url: the file is stored for 24 hours and the reply carries a download link (url, expires_at, bytes, content_type, sha256) instead of the base64, which keeps the file out of your context window.",
      +  "enum": [
      +    "base64",
      +    "url"
      +  ],
      +  "title": "Output",
      +  "type": "string"
      +}
    • addedOutput schema / properties / expires_at
      Added value: +{
      +  "type": [
      +    "string",
      +    "null"
      +  ]
      +}
    • addedOutput schema / properties / sha256
      Added value: +{
      +  "type": [
      +    "string",
      +    "null"
      +  ]
      +}
    • addedOutput schema / properties / url
      Added value: +{
      +  "type": [
      +    "string",
      +    "null"
      +  ]
      +}
  4. Changed3 schema fields changed
    • changedInput schema / properties / text / description
      Previous value: -"English text to speak, 1 to 2,000 characters."New value: +"Text to speak, 1 to 2,000 characters, in the language of the chosen voice (English, Spanish, French, Hindi, Italian or Brazilian Portuguese)."
    • changedInput schema / properties / voice / description
      Previous value: -"Voice: af_heart, af_bella, af_nicole, af_sarah (US female), am_adam, am_michael (US male), bf_emma (UK female), bm_george (UK male)."New value: +"Voice (41): the first letter is the language: a US English (af_heart default, af_bella, am_adam), b UK English (bf_emma, bm_george), e Spanish (ef_dora), f French (ff_siwis), h Hindi (hf_alpha, hm_omega), i Italian (if_sara, im_nicola), p Brazilian Portuguese (pf_dora, pm_alex); f = female, m = male. Write the text in the voice's language."
    • changedInput schema / properties / voice / enum
      Previous value: -[
      -  "af_heart",
      -  "af_bella",
      -  "af_nicole",
      -  "af_sarah",
      -  "am_adam",
      -  "am_michael",
      -  "bf_emma",
      -  "bm_george"
      -]New value: +[
      +  "af_heart",
      +  "af_alloy",
      +  "af_aoede",
      +  "af_bella",
      +  "af_jessica",
      +  "af_kore",
      +  "af_nicole",
      +  "af_nova",
      +  "af_river",
      +  "af_sarah",
      +  "af_sky",
      +  "am_adam",
      +  "am_echo",
      +  "am_eric",
      +  "am_fenrir",
      +  "am_liam",
      +  "am_michael",
      +  "am_onyx",
      +  "am_puck",
      +  "am_santa",
      +  "bf_alice",
      +  "bf_emma",
      +  "bf_isabella",
      +  "bf_lily",
      +  "bm_daniel",
      +  "bm_fable",
      +  "bm_george",
      +  "bm_lewis",
      +  "ef_dora",
      +  "em_alex",
      +  "em_santa",
      +  "ff_siwis",
      +  "hf_alpha",
      +  "hf_beta",
      +  "hm_omega",
      +  "hm_psi",
      +  "if_sara",
      +  "im_nicola",
      +  "pf_dora",
      +  "pm_alex",
      +  "pm_santa"
      +]
  5. Added

TDQS

A4.6/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only declare the generic read/write/idempotency profile, but the description adds substantial non-obvious behavior: offline Kokoro-82M neural synthesis, synthetic-voice disclosure, 422/503/504 error semantics with 'none charged', input text not logged, 24 h retention only for url output, and latency estimates. This is exactly the context annotations cannot carry.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with purpose and the sibling routing, then progressively finer detail (errors, pricing, output handling, latency, docs). Some redundancy: '41 voices' and '6 languages' are stated twice, and the language list at the start duplicates the schema's voice-language table.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 5-parameter generation tool with an output schema and full schema coverage, the description covers everything an agent needs: cost, quota, error codes, latency, output handling and retention. No meaningful gap remains that the schema or output schema would not cover.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3; the description exceeds it by explaining that the voice prefix encodes the language and that text must be written in that language, plus the practical instruction to save data_base64 to a file or request output='url' for a 24 h link. That adds real meaning beyond the enum and field descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with a specific verb and resource ('Speak text aloud in 41 voices') plus the language scope, and immediately distinguishes itself from transcribe_audio by naming the reverse-direction sibling. An agent can identify this as a TTS tool without reading the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

'For audio to text use transcribe_audio' gives an explicit alternative with the condition that selects it, and the description adds practical constraints (2,000-char cap, 5 free calls per IP per UTC day). It stops short of guiding voice/format selection tradeoffs beyond what the schema says, so not a full 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.